Compression and Transmission of Big AI Model Based on Deep Learning

Zhèng-Hóng Lin, Yuzhong Zhou, Yuliang Yang, Jiahao Shi, Jie Lin
{"title":"Compression and Transmission of Big AI Model Based on Deep Learning","authors":"Zhèng-Hóng Lin, Yuzhong Zhou, Yuliang Yang, Jiahao Shi, Jie Lin","doi":"10.4108/eetsis.3803","DOIUrl":null,"url":null,"abstract":"In recent years, big AI models have demonstrated remarkable performance in various artificial intelligence (AI) tasks. However, their widespread use has introduced significant challenges in terms of model transmission and training. This paper addresses these challenges by proposing a solution that involves the compression and transmission of large models using deep learning techniques, thereby ensuring the efficiency of model training. To achieve this objective, we leverage deep convolutional networks to design a novel approach for compressing and transmitting large models. Specifically, deep convolutional networks are employed for model compression, providing an effective means to reduce the size of large models without compromising their representational capacity. The proposed framework also includes carefully devised encoding and decoding strategies to guarantee the restoration of model integrity after transmission. Furthermore, a tailored loss function is designed for model training, facilitating the optimization of both the transmission and training performance within the system. Through experimental evaluation, we demonstrate the efficacy of the proposed approach in addressing the challenges associated with large model transmission and training. The results showcase the successful compression and subsequent accurate reconstruction of large models, while maintaining their performance across various AI tasks. This work contributes to the ongoing research in enhancing the practicality and efficiency of deploying large models in real-world AI applications.","PeriodicalId":155438,"journal":{"name":"ICST Transactions on Scalable Information Systems","volume":"47 3","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICST Transactions on Scalable Information Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4108/eetsis.3803","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

In recent years, big AI models have demonstrated remarkable performance in various artificial intelligence (AI) tasks. However, their widespread use has introduced significant challenges in terms of model transmission and training. This paper addresses these challenges by proposing a solution that involves the compression and transmission of large models using deep learning techniques, thereby ensuring the efficiency of model training. To achieve this objective, we leverage deep convolutional networks to design a novel approach for compressing and transmitting large models. Specifically, deep convolutional networks are employed for model compression, providing an effective means to reduce the size of large models without compromising their representational capacity. The proposed framework also includes carefully devised encoding and decoding strategies to guarantee the restoration of model integrity after transmission. Furthermore, a tailored loss function is designed for model training, facilitating the optimization of both the transmission and training performance within the system. Through experimental evaluation, we demonstrate the efficacy of the proposed approach in addressing the challenges associated with large model transmission and training. The results showcase the successful compression and subsequent accurate reconstruction of large models, while maintaining their performance across various AI tasks. This work contributes to the ongoing research in enhancing the practicality and efficiency of deploying large models in real-world AI applications.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于深度学习的大人工智能模型的压缩与传输
近年来,大型人工智能模型在各种人工智能(AI)任务中表现出了不俗的性能。然而,它们的广泛应用给模型传输和训练带来了巨大挑战。本文针对这些挑战提出了一种解决方案,即利用深度学习技术压缩和传输大型模型,从而确保模型训练的效率。为了实现这一目标,我们利用深度卷积网络设计了一种压缩和传输大型模型的新方法。具体来说,深度卷积网络被用于模型压缩,为缩小大型模型的尺寸提供了有效手段,同时又不影响其表征能力。所提出的框架还包括精心设计的编码和解码策略,以保证在传输后恢复模型的完整性。此外,我们还为模型训练设计了量身定制的损失函数,从而促进了系统内传输和训练性能的优化。通过实验评估,我们证明了所提出的方法在应对与大型模型传输和训练相关的挑战方面的功效。结果表明,我们成功地压缩并随后准确地重建了大型模型,同时在各种人工智能任务中保持了模型的性能。这项研究有助于提高大型模型在现实世界人工智能应用中部署的实用性和效率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Review on DDoS Attack in Controller Environment of Software Defined Network A novel color image encryption method using Fibonacci transformation and chaotic systems Eye Disease Detection Using Deep Learning Models with Transfer Learning Techniques FaceNet – A Framework for Age Variation Facial Digital Images JWTAMH: JSON Web Tokens Based Authentication Mechanism for HADOOP.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1